Abstract
De novo drug design is a computational approach that generates novel molecular structures from atomic building blocks with no a priori relationships. Conventional methods include structure-based and ligand-based design, which depend on the properties of the active site of a biological target or its known active binders, respectively. Artificial intelligence, including ma-chine learning, is an emerging field that has positively impacted the drug discovery process. Deep reinforcement learning is a subdivision of machine learning that combines artificial neural networks with reinforcement-learning architectures. This method has successfully been em-ployed to develop novel de novo drug design approaches using a variety of artificial networks including recurrent neural networks, convolutional neural networks, generative adversarial networks, and autoencoders. This review article summarizes advances in de novo drug design, from conventional growth algorithms to advanced machine-learning methodologies and high-lights hot topics for further development.
Highlights
The development of a chemical entity and its testing, evaluation, and authorization to become a marketed drug is a laborious and expensive process that is prone to failure [1].it is estimated that just 5 in 5000 drug candidates make it through preclinical testing to human testing and just one of those tested in humans reaches the market [2].The discovery of novel chemical entities with the desired biological activity is crucial to keep the discovery pipeline going [3]
For a compound to be relevant, it has to reach a balance between several contrasting aspects, which include the right amount of novelty: it should not be too similar to known drugs and not too different so as to be completely unpredictable; it has to be stable and synthesizable; it should be feasible to produce; and it should score highly in the prediction of its desired properties
It is especially important to test the capability of producing a wide variety of new structures when working with deep generative models, as failure may happen where the generated samples lack variety or the generated samples resemble the mean of the training distribution too much
Summary
The development of a chemical entity and its testing, evaluation, and authorization to become a marketed drug is a laborious and expensive process that is prone to failure [1].it is estimated that just 5 in 5000 drug candidates make it through preclinical testing to human testing and just one of those tested in humans reaches the market [2].The discovery of novel chemical entities with the desired biological activity is crucial to keep the discovery pipeline going [3]. The development of a chemical entity and its testing, evaluation, and authorization to become a marketed drug is a laborious and expensive process that is prone to failure [1]. The design of novel molecular structures for synthesis and in vitro testing is vital for the development of novel therapeutics for future patients. Advances in high-throughput screening of commercial or in-house compound libraries have significantly enhanced the discovery and development of small-molecule drug candidates [4]. Despite the progress that has been made in recent decades, it is well-known that only a small fraction of the chemical space has been sampled in the search for novel drug candidates. Medicinal and organic chemists face a great challenge in terms of selecting, designing, and synthesizing novel molecular structures suitable for entry into the drug discovery and development pipeline.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have